A joint machine learning and modelling approach to explore the prognostic potential of inflammatory patterns in breast tissue
Homeostasis in healthy breast tissue depends on tightly regulated balance between epithelial cell proliferation and aptoptosis. In cooperation with the Department of Pathology at the Medical School of Hannover, we developed a multiscale cell-based model for the interactions between immune and epithelial cells in lobular epithelium with normal cell turnover rates during the menstrual cycle. Physiological parameters were calibrated based on comprehensive spatial data extracted from digital whole-slide images (WSI). We established a modular workflow to detect regions of interest (lobular structures) by a texture and machine learning based region classification procedure, and measured the number of lymphocytes and epithelial cells based on a novel technology for robust nucleus detection. The integrative modelling environment allowed to identify predictive and prognostic spatio-temporal interaction patterns of immune cells in the context of lymphocytic lobulitis, thus expanding immune contexture evaluation beyond mere counting of various immune cell subsets. This represents a step forward towards extended, more comprehensive criteria for breast tissue biopsy evaluation, specifically supporting the development of novel prognostic/dynamic markers, and companion biomarkers guiding for immunomodulatory therapeutic interventions.
Haralampos Hatzikirou, Alexey Uvarovskii (former member), Ghazal Montaseri (former member), Sahamoddin Khailaie, Michael Meyer-Hermann
Friedrich Feuerhake (Medizinische Hochschule Hannover)
Schaadt NS, Schönmeyer R, Forestier G, Brieu N, Braubach P, Nekolla K, Meyer-Hermann M, Feuerhake F. Graph-based description of tertiary lymphoid organs at single-cell level. PLoS Comput Biol 2019; in press.
Schaadt NS, Alfonso JCL, Schönmeyer R, Grote A, Forestier G, Wemmert C, Krönke N, Stoeckelhuber M, Kreipe HH, Hatzikirou H, Feuerhake F. Image analysis of immune cell patterns in the human mammary gland during the menstrual cycle refines lymphocytic lobulitis. Breast Cancer Res 164 (2017) 305-315.
Alfonso JCL, Schaadt NS, Schönmeyer R, Brieu N, Forestier G, Wemmert C, Feuerhake F, Hatzikirou H. In silico insights on the prognostic potential of immune cell infiltration patterns in the breast lobular epithelium. Sci Rep 6 (2016) 33322.
- Systems Immunology- Prof. Dr. Michael Meyer-Hermann
BMBF - Federal Ministry of Education and Research